In https://chatgpt.com/share/94152e76-7511-4943-9d99-1118267f4b2b I gave the new model a challenging complex analysis problem (which I had previously asked GPT4 to assist in writing up a proof of in https://chatgpt.com/share/63c5774a-d58a-47c2-9149-362b05e268b4 ). Here the results were better than previous models, but still slightly disappointing: the new model could work its way to a correct (and well-written) solution *if* provided a lot of hints and prodding, but did not generate the key conceptual ideas on its own, and did make some non-trivial mistakes. The experience seemed roughly on par with trying to advise a mediocre, but not completely incompetent, graduate student. However, this was an improvement over previous models, whose capability was closer to an actually incompetent graduate student. It may only take one or two further iterations of improved capability (and integration with other tools, such as computer algebra packages and proof assistants) until the level of "competent graduate student" is reached, at which point I could see this tool being of significant use in research level tasks. (2/3)
僕でもわかる継続と部分継続
https://mametter.hatenablog.com/entry/20080417/p1
pointer provenance?
https://queue.acm.org/detail.cfm?id=3212479&utm_source=perplexity
追っかけ
TiDBソースコード輪読会 #2
https://zenn.dev/nakagawa_satoya/books/tiug-2024-08-20
午後問2まで
対策セミナー「こう出たR6春セキスペ解答解説」資料を公開しました(動画あり)
https://www.jp-rissa.or.jp/post/2656/
Intercept HTTP(S) requests to & from Docker containers in your local dev environment
https://trayce.dev/